(Luận văn thạc sĩ) using big data to construct the residential property price index in vietnam the case of ho chi minh city

VIETNAM NATIONAL UNIVERSITY, HANOI VIETNAM JAPAN UNIVERSITY NGUYEN THE HUNG USING BIG DATA TO CONSTRUCT THE RESIDENTIAL PROPERTY PRICE INDEX IN VIETNAM: THE CASE OF HO CHI MINH CITY MAJOR: PUBLIC POLICY CODE: ………………… RESEARCH SUPERVISORS: Dr Vu Hoang Linh Hanoi, 2019 TABLE OF CONTENTS DECLARATION iii ACKNOWLEDGEMENTS iv ABSTRACT v LIST OF ABBREVIATIONS .vi LIST OF AND FIGURES AND TABLE viii CHAPTER INTRODUCTION 1.1 Background of the study 1.2 Rationale of the study .2 1.3 Aims and objectives of the study 1.4 Research instrument .6 1.5 Structure of the study .7 CHAPTER 2.1 LITERATURE REVIEW The Handbook on Residential Property Price Index 2.1.1 Median/mean transactions price 2.1.2 Stratification or Mix adjustment 2.1.3 Repeat-sales 10 2.1.4 Hedonic method .10 2.2 The previous residential property price indexes 12 2.2.1 RPPI of Ireland 12 i 2.2.2 RPPI of Austria 13 2.2.3 RPPI of Malta 14 2.2.4 RPPI of Thailand 15 2.2.5 RPPI of Indonesia 16 2.2.6 RPPI of Savills Vietnam 17 CHAPTER DEVELOPING RPPI IN VIETNAM, THE CASE OF HO CHI MINH CITY 19 3.1 The overview of real estate transaction in Vietnam .19 3.2 The data sources on real estate price in Vietnam 20 3.3 Building big data for RPPI calculating 22 3.4 Calculating RPPI for apartment in Ho Chi Minh City 26 CHAPTER FINDINGS AND DISCUSSIONS 34 CHAPTER POLICY IMPLICATION AND FURTHER STUDY 36 5.1 Policy implication .36 5.2 Further study .38 CHAPTER REFERENCES .40 ii DECLARATION I certify that I myself write this thesis entitled “Using big data to construct the residential property price index in Vietnam: The case of Ho Chi Minh City” It is not a plagiarism or made by others Anything related to others‟ works is written in quotation, the sources of which are listed on the list of references If then the pronouncement proves wrong, I am ready to accept any academic punishment, including the withdrawal or cancellation of my academic degree Signature iii ACKNOWLEDGEMENTS No one can achieve anything without the help of others This thesis could not be completed without priceless assistances of many people I would like to express my gratitude to all of them Firstly of all, I would like to express my deepest thanks of gratitude to my respectable supervisor, Dr Vu Hoang Linh for his friendly and sympathetic assistance and dedicated involvement throughout the process of this thesis With profound knowledge and experience, he helped me improving my research Without his instructions, the thesis would be undone Secondly, I would also like to be grateful to all my dear professors, JICA experts in Vietnam Japan University who conveyed to me numerous courses and knowledge and classmates of the Master of Public Policy, for their helpful as well as practical suggestions I will keep in mind all the memories that we had during my time at Vietnam Japan University Last but not least, I also own a great debt of gratitude to my family and friends for their immeasurable support bot all my degree and in this arduous process of this study iv ABSTRACT Calculating real estate price index is one of the major challenges for statistical agencies around the world However, the need for tools to monitor the real estate market is essential from all levels from micro to macro management Therefore, statistical agencies of some countries in the world and some real estate companies like Savill Vietnam have built their own methods based on their actual conditions to calculate this index Thus, it might be impossible to compare the results Recently, international statistical organizations have jointly published a manual to guide the general methodology for calculating this indicator In addition, the development of information technology has also brought many new tools to serve economic management including big data sources This study attempts to develop the residential property price index (RPPI) in Vietnam with specific in the apartment market in Ho Chi Minh City using big data from property advertisement web portals as a prototype The hedonic regression method is used to calculate this index The research results show that the calculation residential property price index from big data source is completely feasible and that is suggestions for using big data to calculate other statistical indicators Keywords: Big data, Hedonic Regressions, Ho Chi Minh City apartment, Residential Property Price Index, web crawler v LIST OF ABBREVIATIONS ABS: Australian Bureau of Statistics API: Application Programming Interface BDP: Big data processing BI: Bank of Indonesia CSO: Central Statistics Office of Ireland Eurostat: The statistical office of the European Union GDP: Gross Domestic Product GRDP: Gross Regional Domestic Product GSO: The General Statistics Office of Vietnam HoREA: Ho Chi Minh Real Estate Association ILO: International Labor Organization IMF: International Monetary Fund MAD: Median absolute deviation MPD: Mobile position data NER: Named Entity Recognition OECD: The Organisation for Economic Co-operation and Development RPPI: Residential Property Price Index vi RFID: Radio Frequency Identification SDGs: Sustainable Development Goals SBV: State Bank of Vietnam UNECE: The United Nations Economic Commission for Europe WB: The World Bank vii LIST OF AND FIGURES AND TABLE List of figures Figure 1.1 Five characteristics of Big data Figure 3.1 The house selling/ buying flow in Vietnam .19 Figure 3.2 The Flow of building database 24 Figure 3.3 Map of apartments advertised in Ho Chi Minh city 25 Figure 3.4 Extract data fields from advertisements 26 Figure 3.5 Distribution of Price 29 Figure 3.6 RPPI_aparment of Hochiminh City with Jan, 2018 is reference .33 List of Tables Table 3.1 Summary statistics of database 28 Table 3.2 Dummy Hedonic Regression result 30 Table 3.3 RPPI_apartment in Ho Chi Minh city with Mar,2018 is reference 32 Table 3.4 RPPI_apartment in Ho Chi Minh city with Jan,2018 is reference 32 viii ix The model does not mention the quality of construction because all apartment buildings that are allowed to be built must comply with construction standards of Vietnam At the same time, the Ministry of Construction of Vietnam has no standards for the classification of formal apartments according to criteria such as high-class, intermediate or popular Therefore, this type of apartment has not been mentioned From January, 2018 to August, 2018 the database contains 106,518 observations After removing the spurious values of price data and the outliers‟ value, the database for calculating is 77,076 observations with the summary statistics: Table 3.1 Summary statistics of database Price (mil vnd) Size (m2) Restroom bedroom Min : 495 Min : 47.11 Min : Min : 1st Qu.: 1450 1st Qu.: 62 1st Qu.: 1st Qu.: Median : 1900 Median : 70 Median : Median : Mean : 2236 Mean : 73.65 Mean : 1.848 Mean : 2.088 3rd Qu.: 2800 3rd Qu.: 81 3rd Qu.: 3rd Qu.: Max : 5590 Max : 136.6 Max : Max : (Source: author) 28 Figure 3.5 Distribution of Price The Hedonic regression model with the equation was applied: ln 𝑃𝑡 = 𝑡 𝛽0 12 + 𝛽𝑘 𝑋𝑘 + 𝑘=1 𝛼𝑗 𝑇𝐷𝑗 𝑗 =2 Where: Pt = price ; 𝛽0𝑡 = intercept; Xk = residential characteristics: - the number of bedrooms; - the number of restroom; - size of apartment (m2); - Location (district as the dummy variable); 29 TD = Time dummy In this model, March was chosen as the reference because it has the most observations in this sample Table 3.2 Dummy Hedonic Regression result Coefficients: Estimate Std Error t value Pr(>|t|) (Intercept) 6.730e+00 5.440e-03 1237.066 < 2e-16 *** size 1.267e-02 5.837e-05 217.097 < 2e-16 *** factor(restroom_catg)1 -3.024e-02 2.958e-03 -10.223 < 2e-16 *** factor(bedroom_catg)1 8.924e-02 4.071e-03 21.924 < 2e-16 *** factor(year_month)201801 -4.779e-02 3.664e-03 -13.043 < 2e-16 *** factor(year_month)201802 -9.900e-03 2.884e-03 factor(year_month)201804 6.832e-03 2.291e-03 -3.433 0.000597 *** 2.982 0.002862 ** factor(year_month)201805 2.558e-02 2.350e-03 10.886 < 2e-16 *** factor(year_month)201806 7.352e-02 5.968e-03 12.318 < 2e-16 *** factor(year_month)201807 6.988e-02 7.458e-03 9.371 < 2e-16 *** factor(year_month)201808 5.173e-02 7.134e-03 7.250 4.2e-13 *** factor(district)760 4.667e-01 1.358e-02 34.377 < 2e-16 *** factor(district)761 -3.668e-01 4.403e-03 -83.298 < 2e-16 *** factor(district)762 -3.006e-01 4.366e-03 -68.845 < 2e-16 *** factor(district)763 -2.528e-01 4.318e-03 -58.534 < 2e-16 *** factor(district)764 -1.301e-01 6.112e-03 -21.292 < 2e-16 *** factor(district)765 2.154e-01 4.742e-03 45.431 < 2e-16 *** factor(district)766 1.062e-01 4.877e-03 21.779 < 2e-16 *** factor(district)767 -1.137e-01 3.843e-03 -29.582 < 2e-16 *** factor(district)768 3.638e-01 7.144e-03 50.923 < 2e-16 *** factor(district)769 1.579e-01 3.291e-03 47.994 < 2e-16 *** factor(district)770 4.446e-01 1.601e-02 27.774 < 2e-16 *** factor(district)771 4.811e-01 5.567e-03 86.419 < 2e-16 *** factor(district)772 1.139e-01 1.081e-02 10.539 < 2e-16 *** 30 factor(district)773 3.687e-01 3.957e-03 93.189 < 2e-16 *** factor(district)774 3.217e-01 1.080e-02 29.778 < 2e-16 *** factor(district)775 -4.552e-02 5.171e-03 -8.804 < 2e-16 *** factor(district)776 -2.696e-01 3.143e-03 -85.792 < 2e-16 *** factor(district)777 -4.538e-01 4.858e-03 -93.414 < 2e-16 *** factor(district)784 -5.864e-01 4.203e-02 -13.952 < 2e-16 *** factor(district)785 -3.073e-01 5.126e-03 -59.946 < 2e-16 *** factor(district)786 -3.103e-01 5.011e-03 -61.923 < 2e-16 *** Signif codes: ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ Residual standard error: 0.2337 on 77044 degrees of freedom Multiple R-squared: F-statistic: 0.7234, Adjusted R-squared: 6501 on 31 and 77044 DF, 0.7233 p-value: < 2.2e-16 The result shows that the adjusted R- square is 0,7233 meaning that 72,33% of the variance for a dependent variable that's explained by variables in this regression model With these P-values, all of independent variables have statisticial significances Apply the formular to calculate the index for month t is given by: 𝑒 𝜕𝑡 𝐼𝑡 = 𝜕 × 𝐼𝑡−1 𝑒 𝑡−1 Where: 𝐼𝑡 is the index in month t 𝐼𝑡−1 is the index in month t-1 𝛿𝑡 is a vector of time period coefficients 31 From this result, the RPPI_apartment in Ho Chi Minh city was calculated as belows: Table 3.3 RPPI_apartment in Ho Chi Minh city with Mar,2018 is reference RPPI index Month.year (exponentiation/ anti log of time dummy coefficients) Mar, 2018 =100 Jan, 2018 95.33 Feb, 2018 99.01 Mar, 2018 100.00 Apr, 2018 100.69 May, 2018 102.59 Jun, 2018 107.63 Jul, 2018 107.24 Aug, 2018 105.31 (Source: author) Table 3.4 RPPI_apartment in Ho Chi Minh city with Jan,2018 is reference RPPI index Month.year (Jan, 2018 =100) Jan,2018 100.00 Feb,2018 103.86 32 Mar,2018 104.89 Apr,2018 105.61 May,2018 107.61 Jun,2018 112.90 Jul,2018 112.49 Aug,2018 110.46 (Source: author) RPPI(apartment)_HCM city 115,00 112,90 112,49 110,46 107,61 105,00 103,86 104,89 105,61 100,00 95,00 Figure 3.6 RPPI_aparment of Hochiminh City with Jan, 2018 is reference (Source: author) 33 CHAPTER FINDINGS AND DISCUSSIONS The calculation results for the apartment price index in Ho Chi Minh City continuously increased in the first months of 2018 and decreased in the July and August, 2018 This trend is in line with the opinion of real estate experts In the first haft of year 2018, people's demand for housing has risen sharply while banks and financial institutions have offered incentives to help people buy houses and large value assets (Zing.vn 2018) The July and August of Gregorian calendar are corresponding to the July of Lunar calendar In the Vietnam culture, this month does not bring the lucky to the buyer so that the price went down This result is also consistent with the report of the authorities, real estate association and real estate company According to the Economic and social situation in 2019 of the Ho Chi Minh city Statistics Office, the economic of Ho Chi Minh City in the first months of 2018 continue to show positive changes After a strong increase in the first quarter of 2018 at 7.64%, the highest level since 2016 increased at the highest level since 2016, the Gross Regional Domestic Product (GRDP) of Ho Chi Minh City continued to increase by 7.27% in the second quarter In which, the real estate business service raised by 5,32%, is one of the key sectors contributing to the city's GRDP growth.According to this report, the growth of the real estate service industry has made a significant contribution from the price increase due to there was a time when speculation appeared, increasing unusual land prices and spreading to other places, especially in the Thu Duc district, district and district 34 In the third quarter of 2019, the GRDP of Ho Chi Minh City continues to reach 7.89% and the real estate business service continue to be a driving force for this growth with 9,64% moving up The reasing of housing price is also mentioned in this report as a consequence of the rumors surrounding the expansion of traffic routes The Ho Chi Minh Real Estate Association (HoREA) reported the real estate market in Ho Chi Minh city in the first half of 2018 on report By which, the supply of apartments in Ho Chi Minh City decreased sharply by 45% compared to the same period in 2017 As the result, the price of apartment in Ho Chi Minh recorded the significant increases from December, 2017 In addition, the infrastructure is getting better and better, with the continuous improvement of the airport and port system, roads connecting with neighboring provinces are also gradually completed (Long Thanh - Dau Giay highway, Ben Luc highway Long Thanh, Ring Roads 1, 2, 3, Metro Line No ) also the driving force for this price increase The price increase of the Ho Chi Minh City real estate market is not only reflected in reports of state agencies but also in reports of real estate service companies According to Savills Vietnam, the Savills Property Price Index (SPPI) in Ho Chi Minh City has increased continuously in the first and quarters of 2018 In particular, the increase in the second quarter of 2018 was recorded as the highest increase in years Comparing the above results with the results of RPPI calculation of this study, the increase may be different due to differences in scope, method and data sources but the trend of price fluctuation is the same 35 In addition, the RPPI calculation method of this study complies with the guidelines of the international statistical agencies combined with the experience of some of the previous countries with similar socio-economic circumstances as Indonesia This result is reliable for use in other economic analyzes CHAPTER 5.1 POLICY IMPLICATION AND FURTHER STUDY Policy implication Big Data is a interesting source for official statistics (Glasson et al., 2013) as it enables the potential production of speedy and considerable relevant official figures at relatively low costs Many statistics agencies consider big data as a new data source for official statistics in the compilation of official statistics for the purpose of evidencebased decision making Innovations are needed in the daily production of official statistics, which requires real partnerships with the private sector, new skills and infrastructure, and clear links between available Big Data sources and the Sustainable Development Goals (SDGs) indicators The Statistics Bureau of Japan uses big data to compiling Consumption Trend Index, the Australian Bureau of Statistics uses big data to compile the Consumer price Index, and the Statistics Netherlands compiles some indicates such as road sensor, population at noon also based on big data The more importance, The United Nation Statistical Commission agreed at its 45th session to create the Global Working Group (GWG) on Big Data for Official Statistics to further investigate the benefits and challenges of Big Data, 36 including the potential for monitoring and reporting on the sustainable development goals Other while, many conferences have hosted by statistics international bodies like the United Nations Statistics Division, International Monetary Fund, the statistical office of the European Union, International Labor Organization,… Up to now in Vietnam, all of indicators are compiled from survey data The Viet Nam Statistical Development Strategy 2011-2020, Vision to 2030, signed by The Prime Minister, has identified that application information technology on statistical production is one of main goals of official statistics system Consequently, the calling big data in official statistics is fitting with the requirement of internal and the trend of external This study has shown that the calculation of the real estate price index, as one of the indicators of the national statistical indicator system, from big data source is completely feasible in Vietnam With the advantages of big data and taking experiences from other countries, Vietnam should consider the use of big data in state statistics as a necessary issue to produce more policy-reflecting figures than socio-economic status in terms of saving time and financial resources In the current conditions of Vietnam, besides calculating RPPI, some areas can apply big data to produce statistics such as (1) calculating and now-casting consumer price index from the price listed on the website of supermarkets and online shopping websites, (2) calculating the number of inbound tourists, migration based on the mobile position data (MPD) from telecommunication service providers (3) determine the phase growth of rice plant using machine learning through photos of smartphones and satellites with high resolution However, according to statistic law 2015, official statistics in Vietnam are based on only three main sources of data: 37 Statistical survey Administrative data Statistical Reporting regime It is therefore necessary to supplement the big data source for official statistics in the new law 5.2 Further study This study reviews the methodology of RPPI calculations based on country experience as well as the international guidelines from OECD handbook The study also analyzes the advantages and disadvantages of real estate price data sources in Vietnam, thus provides the most appropriate method adapted to Vietnam's context With the increasing popularity of the internet in Vietnam and the support of information technology, the compilation of big data on real estate in Vietnam is feasible, qualifying to apply the Hedonic regression method in RPPI calculations By employing time dummy hedonic method I have computed residential property price index for the market in Ho Chi Minh City based on the web listing property advertisement The Hedonic indexes compilation showed a promising result and has the potential to become official RPPI in the future The regression outputs represent robust “baseline” models for index compilation The web listing advertisement observations seem more homogenous in nature, -as indicated by high explanatory power given limited characteristics variables available Smoothing may give a better option for the published index in order to reduce short-term volatility 38 For further development, I keep these baseline models to extend the coverage to other large cities like Hanoi, Da Nang, Khanh Hoa This extension will depend on the suitability of the listing data and the relative importance of cities according to the national property market share derived from mortgage data I need to keep the new index remains representative of the current market condition by regularly reviewing the model performance by including a more granular spatial adjustment and other characteristics (such as age of property, infrastructure, direction of the apartment, etc.) in the future 39 CHAPTER REFERENCES Abhiman Das, Manjusha Senapati and Joice John (2009): Hedonic Quality Adjustments for Real Estate Prices in India, Reserve Bank of India Occasional Papers Vol 30, No 1, Summer 2009 Andrew Kanutin, Martin Eiglsperger: The measurement of euro area property prices pitfalls and progress Available at https://www.bis.org/ifc/events/7ifcconf_kanutin_eiglsperger.pdf Bank of Thailand (2015): RPPI progress and plans, Seminar on RPPI in Singapore Borg, K (2004): Constructing a Price Hedonic Property Index for Malta, University of Malta, Msida Bourassa, S.C., Hoesli, M and Sun, J (2006): A simple alternative house price index method, Journal of Housing Economics, Vol 15 No 1, pp 80-7 Central Statistics Office of Ireland (2016): Launch of new Residential Property Price Index (RPPI) Accessed September 25, 2018 from https://www.cso.ie/en/media/csoie/newsevents/presentations/RPPIPr_Conference.pdf Chihiro Shimizu, Kiyohiko G Nishimura and Tsutomu Wanatabe (2011): House Prices at Different Stages of the Buying/Selling Process, Research Center for Price Dynamics- Institute of Economic Research, Hitotsubashi University Chihiro Shimizu, Erwin Diewert, Kiyohiko Nishimura and Tsutomu Watanabe (2014): Residential Property Price Indexes for Japan: An Outline of the Japanese Official RPPI, Discussion Paper 14-05, School of Economics, University of British Columbia Diewert, W.E., S Heravi and M Silver (2009), “Hedonic Imputation Versus Time Dummy Hedonic Indexes”, pp 161-196 in Price Index Concepts and Measurement, W.E Diewert, J Greenlees and C Hulten (eds.), NBER Studies in Income and Wealth, Chicago: University of Chicago Press Eurostat (2010): Experimental house price indices for the Euro Area and the European Union Accessed September 20, 2018 http://epp.eurostat.ec.europa.eu/portal/page/portal/hicp/documents/Tab/Tab/METHHPI_Research_paper_2010-12.pdf 40 from European Commission (2010): Experimental House Price Indices for the Euro Area and European Union Eurostat (2013), Handbook on Residential Property Price Indices GouriÈroux, C and LaferrËre, A (2009): Managing hedonic housing price indexes: The French experience, Journal of Housing Economics Volume 18, Issue 3, September 2009, Pages 206-213 Hoang Huu Phe & Patrick Wakely (2000): Status, Quality and the Other Trade-Off: Towards a New Theory of Urban Residential Location, in Urban Studies, No 1, Vol 37, Taylor & Francis] Hill, R and Melser, D (2005): Constructing panel price indexes using hedonic methods: the case of house prices in Sydney, unpublished, University of New South Wales, Sydney Hill, R.J., D Melser and B Reid (2010), “Hedonic Imputation with Geospatial Data: An Application of Splines to the Housing Market”, Mimeo International Monetary Fund (July, 2018): World Economic Outlook: Vietnam Kich cau mua nha, sam xe mua cuoi nam Accessed September 25, 2018 from https://news.zing.vn/kich-cau-mua-nha-sam-xe-mua-cuoi-nam-post812936.html Joseph Falzon, David Lanzon (2013): Comparing alternative house price indices: evidence from asking prices in Malta, International Journal of Housing Markets and Analysis Vol No 1, 2013 page 98-135 Knight, J (2002): Listing Price, Time on Market, and Ultimate Selling Price: Causes and Effects of Listing Price Changes Real Estate Economics 30 (2) 212–237 Mick Silver (2016): How to Better Measure Hedonic Residential Property Price Indexes, IMF Working Paper No 16/213 Moore (2018): Vietnam Digital Landscape 2018 report Niall O‟Hanlon (2011): Constructing a National House Price Index for Ireland, Journal of the Statistical and Social Inquiry Society of Ireland, Vol XL Nguyen Manh Hung, Tran Van Trong, Ly Hung Thanh, Tran Thanh Hung, Hoang Huu Phe (2008): Evaluation real estate using the theory of location and quality, The cadastral journal 41 Nguyen The Hung (2018): “Determination of impact factor on the real estate price: The approach from internet advertisements”, The Statistical Scientific Information, The Institute of Statistical Science, General Statistics Office of Vietnam, February 2018 Ohnishi, T., T Mizuno, C Shimizu, and T Watanabe (2010): On the Evolution of the House Price Distribution, Research Center for Price Dynamics Working, Paper Series No 61, August 2010 Triplett, J.E (2006), Handbook on “Hedonic Indexes and Quality Adjustments in Price Indexes”; Special Application to Information and Technology Products, Directorate for Science, Technology and Industry, Paris: OECD We Are Social, Digital in 2017: A study of Internet, Social Media, and Mobile use throughout the region of Southeast Asia Wolfgang Brunauer, Wolfgang Feilmayr, Karin Wagner: A New Residential Property Price Index for Austria Accessed September 25, 2018 from https://www.oenb.at/dam/jcr:c2fb0be85a1a-4e58-94dc-175b8984ca56/stat_2012_q3_analyse_brunauer_tcm14-249405.pdf 42 ... this thesis entitled ? ?Using big data to construct the residential property price index in Vietnam: The case of Ho Chi Minh City? ?? It is not a plagiarism or made by others Anything related to others‟... transactions price Using the indicators of the main inclination from the distribution of housing price for purchased houses during the period is one of the easiest way to calculate house prices As residential. .. management including big data sources This study attempts to develop the residential property price index (RPPI) in Vietnam with specific in the apartment market in Ho Chi Minh City using big data